Search results

This paper presents a method for auto-tuning interactive ray tracing on GPUs using a hardware model. Getting full performance from modern GPUs is a challenging task. Workloads which require a guaranteed performance over several runs must select parameters for the worst performance of all runs. Our method uses an analyti- cal GPU performance model to predict the current frame’s render- ing time usi

Scaling the amount of resources allocated to an application according to the actual load is a challenging problem in cloud computing. The emergence of autoscaling techniques allows for autonomous decisions to be taken when to acquire or release resources. The actuation of these decisions is however affected by time delays. Therefore, it becomes critical for the autoscaler to account for this pheno

The growing complexity of signal processing algorithms and platforms poses significant challenges to design methods and implementation tools. High-level dataflow programs, such as those in MPEG's RVC-CAL language, provide abstraction and the opportunity for extensive design-space exploration, but they do raise the problem of efficient automatic synthesis to hardware and software. This paper presen

Multi-sample anti-aliasing is a popular technique for reducing geometric aliasing (jagged edges) and is supported in all modern graphics processors. With multi-sampling anti-aliasing, visibility and depth are sampled more than once per pixel, while shading is done only once per pixel per primitive. Although this significantly reduces the appearance of jagged edges around object boundaries, the ima

We present novel solutions to previously unsolved prob-lems of relative pose estimation from images whose calibration parameters, namely focal lengths and radial distortion, are unknown. Our approach enables metric reconstruction without modeling these parameters. The minimal case for reconstruction requires 13 points in 4 views for both the calibrated and uncalibrated cameras. We describe and imp

Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors based on the image gradient are extremely fast and accurate, but lack robustness in noisy images and challenging conditions. Their learned counterparts are more

This paper reports on a case study in which an at- size application is ported onto a commercially available processor array. Its purpose is threefold: (1) Determine the suitability of processor arrays for this kind of application. (2) Develop a runtime software infrastructure that supports streaming applications on processor arrays. (3) Gather data and insights into the resulting system performanc

With the arrival of heterogeneous manycores comprising various features to support task, data and instruction-level parallelism, developing applications that take full advantage of the hardware parallel features has become a major challenge. In this paper, we present an extension to our CAL compilation framework (CAL2Many) that supports data parallelism in the CAL Actor Language. Our compilation f

The problem of joint source-channel coding is considered for a stationary remote (noisy) Gaussian source and a Gaussian channel. The encoder and decoder are assumed to be causal and their combined operations are subject to a delay constraint. It is shown that, under the mean-square error distortion metric, an optimal encoder-decoder pair from the linear and time-invariant (LTI) class can be found

We propose a depth cache that keeps the depth data in compressed format, when possible. Compared to previous work, this requires a more flexible cache implementation, where a tile may occupy a variable number of cache lines depending on whether it can be compressed or not. The advantage of this is that the effective cache size increases proportionally to the compression ratio. We show that the dep

We present a novel architecture for flexible control of shading rates in a GPU pipeline, and demonstrate substantially reduced shading costs for various applications. We decouple shading and visibility by restricting and quantizing shading rates to a finite set of screen-aligned grids, leading to simpler and fewer changes to the GPU pipeline compared to alternative approaches. Our architecture int

Dataflow is a natural way of modelling streaming applications, such as multimedia, networking and other signal processing applications. In order to cope with the computational and parallelism demands of such streaming applications, multiprocessor systems are replacing uniprocessor systems. Mapping and scheduling these applications on multiprocessor systems are crucial elements for efficient implem

We study the joint design of optimal linear MIMO encoders and decoders for filtering and transmission of a vector- valued signal over parallel Gaussian channels subject to a real- time constraint. The objective is to minimize the sum of the estimation error variances at the receiving end. The design problem is nonconvex, but it is shown that a global optimum can be found by solving a related two-s